Executive Viewpoint: Heavy industry, light footprint—Helping the HPI run leaner and cleaner with AI
GINO HERNANDEZ, Head of Global Digital Business, ABB
The hydrocarbon processing industry (HPI) is at a pivotal juncture, driven by rising global energy demands and mounting pressure for environmental sustainability. The sector must strike a balance between optimizing operations and minimizing carbon footprint. Achieving this goal necessitates more than just intent—it requires intelligence. By embedding artificial intelligence (AI) and advanced data analytics into operational frameworks, the industry can make meaningful progress toward greater sustainability and efficiency.
Historically, the HPI has been a cornerstone of industrial development, providing essential fuels and chemicals that are crucial not only to other heavy industries, but to businesses and people worldwide.
However, the sector is also a significant contributor to global greenhouse gas (GHG) emissions. According to the International Energy Agency (IEA), the oil and gas industry accounts for approximately 15% of global energy-related emissions. To align with international climate goals, operators must adopt, at pace, innovative strategies and technologies that enhance efficiency and reduce environmental impact.
AI has the potential to effect a real change. By harnessing vast amounts of operational data, AI can support process optimization, help to predict equipment failures and better facilitate the integration of renewable energy sources. These capabilities can improve asset performance as well as operational sustainability.
One of the key concerns for the HPI is managing energy use, which is especially critical given the inherently energy-intensive nature of the industry. AI-driven digital solutions can analyze real-time data to adjust operational parameters dynamically. This continuous optimization leads to reduced energy consumption and improved process stability.
AI can also enhance utility management by forecasting energy demand and adjusting supply accordingly. This predictive capability ensures that energy resources are utilized efficiently, minimizing waste and reducing costs–an important consideration as the sector strives to improve efficiencies and maximize return on investment.
The integration of renewable energy sources, such as solar and wind, into refining and processing operations presents both opportunities and challenges. The intermittent nature of renewables requires sophisticated management to ensure consistent energy supply.
AI can address this challenge by predicting renewable energy generation patterns and aligning them with operational demands. For example, AI algorithms can forecast solar irradiance and wind speeds, allowing facilities to plan energy usage proactively. This synchronization ensures that renewable energy is utilized effectively, reducing reliance on fossil fuels.
Additionally, AI can help to manage energy storage systems, determining optimal charging and discharging cycles based on predicted energy generation and consumption. This capability enhances the reliability of renewable energy integration, supporting the transition toward cleaner energy sources.
Unplanned equipment downtime can have significant financial and operational repercussions. AI-driven predictive maintenance offers a solution by learning and predicting potential equipment failures before they occur.
By analyzing data from sensors and historical maintenance records, AI can detect patterns indicative of impending failures. This early detection enables maintenance teams to address issues proactively, reducing downtime and maintenance costs. A study by McKinsey & Company found that predictive maintenance can reduce maintenance costs by up to 30% and decrease unplanned outages by up to 50%.
As an example, our organization's AI-driven predictive maintenance solution is being used by a European producer to improve efficiency and reliability while optimizing asset performance and lowering costs. This project demonstrates our ongoing efforts to bring predictive analytics together to prevent electrical, rotating, instrumentation and even IT equipment failures.
This solution has been able to predict numerous major faults; preventing unplanned shutdowns and potential environmental impact.
ABB helped the producer to make the switch from time-based maintenance to condition-based and predictive maintenance. We estimate that predictive analytics increased production capability by 10% and maintenance savings by up to 2%.
Safety is paramount in the HPI, where operations involve hazardous materials and processes. AI can enhance safety by monitoring real-time operations, detecting anomalies and triggering alerts or corrective actions to prevent incidents.
Furthermore, AI can assist in regulatory compliance by continuously ensuring adherence to safety and environmental standards, reducing the risk of violations and penalties.
While the benefits of AI are substantial, successful implementation requires careful planning and execution. Ensuring compatibility and integration with existing technologies is the first step in helping to minimize disruptions. Equally important are employee training and development programs to support the integration – and to maximize the opportunities to successfully leverage new AI systems.
The transition toward intelligent, sustainable operations in the HPI is a complex endeavor. Partnerships between technology providers, operators and regulatory bodies can facilitate the development and adoption of AI solutions tailored to the industry's unique needs.
Moreover, sharing best practices and success stories can accelerate learning and encourage broader implementation. Industry forums, such as those hosted by Hydrocarbon Processing, provide valuable platforms for knowledge exchange and collaboration.
By embracing AI, operators can transform intent into action, leading the way toward a more sustainable and intelligent future. The journey requires commitment, collaboration and a willingness to innovate—but the potential rewards, in terms of operational excellence and environmental stewardship, are substantial.
REFERENCES
1. McKinsey & Company, "How AI can accelerate the energy transition," 2021, online: https://www.mckinsey.com
2. IEA, "Greenhouse gas emissions from the oil and gas sector," 2022.
3. Journal of Petroleum Technology, "Data-Driven Efficiency in Heat Exchanger Maintenance," 2022.
4. ARC Advisory Group, "Predictive Maintenance: Lowering Downtime and Emissions," 2022.
5. World Economic Forum, "Building Resilient Energy Systems: Microgrids in Industry," 2023.
The Author
Gino Hernandez is currently Head of Global Digital Business at ABB Energy Industries. At ABB, he applies his extensive background in digital technologies, business management, finance, sales management, business plan development and model execution to lead global product management and business development teams for Digital applications. In addition to his duties at ABB, he serves as a board member of Lavoro Technologies and Colexas Digital. Previously, Gino served as Rockwell Automation’s Global Oil and Gas Director. He also previously served as Rockwell Automation's, North America Oil & Gas Director and China Oil & Gas Leader. Prior to Rockwell Automation, Gino worked for IBM for nine years in various positions of increasing responsibility.
Comments